相关论文: User-centric Subjective Leaderboard by Customizabl…

Reinforcement learning from human feedback (RLHF) has emerged as the primary method for aligning large language models (LLMs) with human preferences. The RLHF process typically starts by training a reward model (RM) using human preference…

Automatic grading of subjective questions remains a significant challenge in examination assessment due to the diversity in question formats and the open-ended nature of student responses. Existing works primarily focus on a specific type…

Learning from preference feedback is a common practice for aligning large language models~(LLMs) with human value. Conventionally, preference data is learned and encoded into a scalar reward model that connects a value head with an LLM to…

Learning human preferences in language models remains fundamentally challenging, as reward modeling relies on subtle, subjective comparisons or shades of gray rather than clear-cut labels. This study investigates the limits of current…

Recent work in large language modeling (LLMs) has used fine-tuning to align outputs with the preferences of a prototypical user. This work assumes that human preferences are static and homogeneous across individuals, so that aligning to a a…

The recent surge of versatile large language models (LLMs) largely depends on aligning increasingly capable foundation models with human intentions by preference learning, enhancing LLMs with excellent applicability and effectiveness in a…

Personalized alignment is crucial for enabling Large Language Models (LLMs) to engage effectively in user-centric interactions. However, current methods face a dual challenge: they fail to infer users' deep implicit preferences (including…

Effective emotional support hinges on understanding users' emotions and needs to provide meaningful comfort during multi-turn interactions. Large Language Models (LLMs) show great potential for expressing empathy; however, they often…

Alignment of large language models (LLMs) typically involves training a reward model on preference data, followed by policy optimization with respect to the reward model. However, optimizing policies with respect to a single reward model…

In classical Reinforcement Learning from Human Feedback (RLHF), Reward Models (RMs) serve as the fundamental signal provider for model alignment. As Large Language Models evolve into agentic systems capable of autonomous tool invocation and…

A critical factor in the success of decision support systems is the accurate modeling of user preferences. Psychology research has demonstrated that users often develop their preferences during the elicitation process, highlighting the…

Current benchmarks for evaluating Large Language Models (LLMs) often do not exhibit enough writing style diversity, with many adhering primarily to standardized conventions. Such benchmarks do not fully capture the rich variety of…

Large Language Models (LLMs) have demonstrated remarkable capabilities across various domains and are moving towards more specialized areas. Recent advanced proprietary models such as GPT-4 and Gemini have achieved significant advancements…

The impressive performance of large language models (LLMs) has attracted considerable attention from the academic and industrial communities. Besides how to construct and train LLMs, how to effectively evaluate and compare the capacity of…

The rapid development and dynamic nature of large language models (LLMs) make it difficult for conventional quantitative benchmarks to accurately assess their capabilities. We propose report cards, which are human-interpretable, natural…

Recently, Large Language Models (LLMs) have demonstrated a superior ability to serve as ranking models. However, concerns have arisen as LLMs will exhibit discriminatory ranking behaviors based on users' sensitive attributes (\eg gender).…

Personalized preference alignment for large language models (LLMs), the process of tailoring LLMs to individual users' preferences, is an emerging research direction spanning the area of NLP and personalization. In this survey, we present…

Self-Rewarding Language Models propose an architecture in which the Large Language Models(LLMs) both generates responses and evaluates its own outputs via LLM-as-a-Judge prompting, dynamically improving its generative capabilities through…

Unbiased learning to rank (ULTR), which aims to learn unbiased ranking models from biased user behavior logs, plays an important role in Web search. Previous research on ULTR has studied a variety of biases in users' clicks, such as…

Reward models are central to aligning large language models (LLMs) with human preferences. Yet most approaches rely on pointwise reward estimates that overlook the epistemic uncertainty in reward models arising from limited human feedback.…